A grid-connected control method for a photovoltaic synchronous machine stack power generation system

Abstract

This invention relates to the field of photovoltaic (PV) power generation system operation and maintenance technology. The invention provides a grid-connected control method for a PV synchronous generator system. By acquiring PV system data and PV power generation task data, a random forest model is trained to obtain a grid-connected model. PV array operation data and natural environment data are collected to predict power generation. Real-time PV array operation data is compared with predicted data to generate early warning or output grid-connected control parameters. These parameters are compared with real-time system parameters to calculate errors, and a genetic algorithm is used to optimize the grid-connected model. Finally, the system executes the optimized real-time parameters, achieving synchronization with the grid and improving the stability and grid-connected efficiency of the PV power generation system. This invention effectively solves the problem of voltage, frequency, and phase mismatch during grid connection, promoting intelligent operation and maintenance of PV power generation.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation system operation and maintenance technology, and in particular to a grid-connected control method for a photovoltaic synchronous machine stack power generation system. Background Technology

[0002] Photovoltaic synchronous machine stacks, also known as photovoltaic energy storage virtual synchronous machine technology, combine photovoltaic power generation with energy storage systems. By introducing the concept of virtual synchronous generators, the stability of photovoltaic power generation systems is effectively improved. By adjusting the damping coefficient of the energy storage system, low-frequency oscillations in photovoltaic power generation are suppressed, enabling photovoltaic synchronous machine stack power generation systems to maintain stable operation under different operating conditions.

[0003] Grid connection of a synchronous generator stack power generation system usually refers to the connection of a power generation system that uses a synchronous generator as a power generation device to the main power grid. The grid connection process requires the generator's output voltage, frequency, and phase to match the grid voltage, frequency, and phase. In the existing photovoltaic synchronous generator stack power generation system grid connection process, the generator's output voltage is unstable, and the generator's output voltage, frequency, and phase do not match the grid voltage, frequency, and phase. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a grid-connected control method and extraction method for photovoltaic synchronous machine stack power generation systems, which solves the problems of unstable generator output voltage and mismatch between generator output voltage, frequency, and phase and grid voltage, frequency, and phase during the grid connection process of existing photovoltaic synchronous machine stack power generation systems.

[0005] To solve the above-mentioned technical problems, the specific technical solution of the present invention is as follows:

[0006] The grid-connected control method for a photovoltaic synchronous generator stack power generation system provided by the present invention includes:

[0007] Step S101: Obtain photovoltaic system data and photovoltaic power generation task data. The photovoltaic system data includes control commands, photovoltaic module data, inverter data, meteorological data, power generation data, and grid connection control data. Preprocess the photovoltaic system data and photovoltaic power generation task data to obtain preprocessed photovoltaic system data and photovoltaic power generation task data. Train the random forest model with the preprocessed photovoltaic system data and photovoltaic power generation task data to obtain the grid connection model of the photovoltaic synchronous machine stack power generation system.

[0008] Step S102: Collect photovoltaic array operation data and natural environment data, and substitute the collected photovoltaic array operation data and natural environment data into the preset photovoltaic array power generation prediction model to obtain photovoltaic array power generation prediction data.

[0009] Step S103: Obtain real-time photovoltaic array operation data, substitute the real-time photovoltaic array operation data into the photovoltaic array power generation prediction data and compare it. If the real-time photovoltaic array operation data is higher than the photovoltaic array power generation prediction data, then generate photovoltaic array power generation early warning information.

[0010] Step S104: If the real-time photovoltaic array operation data is lower than the photovoltaic array power generation prediction data, then substitute the real-time photovoltaic array operation data into the grid connection model of the photovoltaic synchronous machine stack power generation system and output the grid connection control parameters of the photovoltaic synchronous machine stack power generation system.

[0011] Step S105: Compare the grid-connected control parameters of the photovoltaic synchronous machine stack power generation system with the real-time parameters of the photovoltaic synchronous machine stack power generation system to obtain the parameter comparison error. The parameter comparison error includes output voltage error, frequency error, and phase adjustment error. Obtain historical data of photovoltaic array operation data. Use the historical data of photovoltaic array operation data and the parameter comparison error to optimize the grid-connected model of the photovoltaic synchronous machine stack power generation system using a genetic algorithm. Use the optimized grid-connected model of the photovoltaic synchronous machine stack power generation system to process the real-time photovoltaic array operation data and output the optimized real-time parameters of the photovoltaic synchronous machine stack power generation system. The photovoltaic synchronous machine stack power generation system executes the optimized real-time parameters to achieve synchronization with the grid, converting the electrical energy generated by the photovoltaic synchronous machine stack power generation system into AC power that conforms to the grid standard and realizing the connection with the grid.

[0012] Furthermore, in the grid-connected control method for the photovoltaic synchronous generator stack power generation system of the present invention, step S101 includes:

[0013] The data for the photovoltaic modules includes power, efficiency, and temperature;

[0014] Inverter data includes inverter conversion efficiency and inverter operating status;

[0015] Meteorological data includes solar irradiance, temperature, and wind speed;

[0016] Grid connection control data includes grid connection voltage, grid connection current, and grid connection frequency;

[0017] Photovoltaic power generation task data includes expected power generation, power generation period, and power regulation requirements;

[0018] The random forest model is trained using preprocessed photovoltaic system data and photovoltaic power generation task data as input. After training, the random forest model becomes the grid-connected model of the photovoltaic synchronous machine stack power generation system, which is used to receive new photovoltaic system data and photovoltaic power generation task data, and output grid-connected control parameters.

[0019] Furthermore, in the grid-connected control method for the photovoltaic synchronous generator stack power generation system of the present invention, step S102 includes:

[0020] The operating data of the photovoltaic array includes real-time parameters such as the voltage, current, power, and temperature of the photovoltaic modules.

[0021] The preprocessed photovoltaic array operation data and natural environment data are used as inputs and substituted into the preset photovoltaic array power generation prediction model. The preset photovoltaic array power generation prediction model is started to process the input data and calculate the photovoltaic array power generation prediction data through the preset photovoltaic array power generation prediction model. The photovoltaic array power generation prediction data includes the predicted power generation, the predicted power efficiency, and the predicted power output.

[0022] Furthermore, in the grid-connected control method for the photovoltaic synchronous generator stack power generation system of the present invention, step S103 includes:

[0023] The prediction data for the corresponding time period is obtained from the photovoltaic array power generation prediction model. The real-time photovoltaic array operation data and the photovoltaic array power generation prediction data are aligned in time, that is, the real-time photovoltaic array operation data and the photovoltaic array power generation prediction data correspond to the data at the same point in time or within the same time period.

[0024] The real-time photovoltaic array operation data is compared with the photovoltaic array power generation prediction data item by item to check whether the parameters of the real-time photovoltaic array are higher than the predicted values.

[0025] An early warning is triggered when the power output of the real-time photovoltaic array exceeds the predicted power by 10% for 5 consecutive minutes. The warning includes the triggering time, parameters, and warning level information.

[0026] Furthermore, in the grid-connected control method for the photovoltaic synchronous generator stack power generation system of the present invention, step S104 includes:

[0027] To determine whether the real-time photovoltaic array operating data is lower than the photovoltaic array power generation prediction data, the voltage, current, and power of the real-time photovoltaic array operating data are compared with the photovoltaic array power generation prediction data. If the real-time photovoltaic array operating data is lower than the prediction data, the voltage, current, and power of the real-time photovoltaic array operating data are used as input information.

[0028] The grid connection model of the photovoltaic synchronous machine stack power generation system to be used is determined. The grid connection model of the photovoltaic synchronous machine stack power generation system is established based on historical data, system characteristics and control objectives. The grid connection model of the photovoltaic synchronous machine stack power generation system is used to output grid connection control parameters.

[0029] The real-time photovoltaic array operation data is substituted into the grid-connected model of the photovoltaic synchronous machine stack power generation system, and the voltage, current, and timestamp of the data are correlated with the input variables of the model.

[0030] The grid-connected model of the photovoltaic synchronous machine stack power generation system is started. The grid-connected model of the photovoltaic synchronous machine stack power generation system processes the input real-time photovoltaic array operation data and calculates the grid-connected control parameters.

[0031] The grid-connection control parameters are obtained from the grid-connection model of the photovoltaic synchronous machine stack power generation system. The grid-connection control parameters include output voltage, frequency and phase adjustment. The grid-connection control parameters are used to adjust the output of the photovoltaic synchronous machine stack power generation system so that the photovoltaic synchronous machine stack power generation system is synchronized with the grid.

[0032] Furthermore, in the grid-connected control method for the photovoltaic synchronous generator stack power generation system of the present invention, step S105 includes:

[0033] Obtain the grid-connected control parameters of the photovoltaic synchronous machine stack power generation system output by step S104. The grid-connected control parameters of the photovoltaic synchronous machine stack power generation system are calculated based on the grid-connected model of the photovoltaic synchronous machine stack power generation system, and are intended to synchronize the system output with the grid.

[0034] The actual operating parameters of the photovoltaic synchronous machine stack power generation system are acquired in real time. The actual operating parameters of the photovoltaic synchronous machine stack power generation system include the current output voltage, frequency and phase.

[0035] The grid-connected control parameters and the real-time system parameters are aligned in time, meaning that the grid control parameters and the real-time parameters of the photovoltaic synchronous machine stack power generation system correspond to the same moment.

[0036] The target output voltage, target frequency, and target phase in the grid-connected control parameters are compared item by item with the actual output voltage, actual frequency, and actual phase in the real-time parameters of the photovoltaic synchronous machine stack power generation system. The error value of each parameter is calculated, which is the difference between the real-time value of the photovoltaic synchronous machine stack power generation system and the target value in the grid-connected control parameters.

[0037] For the output voltage, calculate the difference between the actual output voltage and the target output voltage to obtain the output voltage error;

[0038] For frequency, the difference between the actual frequency and the target frequency is calculated to obtain the frequency error;

[0039] For the phase, the difference between the actual phase and the target phase is calculated to obtain the phase adjustment error.

[0040] Furthermore, in the grid-connected control method for the photovoltaic synchronous generator stack power generation system of the present invention, step S105 includes:

[0041] Based on the grid connection requirements and control objectives of the photovoltaic synchronous machine stack power generation system, the optimization objectives are determined. The optimization objectives include minimizing the weighted sum of output voltage error, frequency error and phase adjustment error, as well as the error threshold.

[0042] Based on the optimization objective, a fitness function is constructed, which is used to evaluate the grid-connected model under given parameters;

[0043] Determine the parameters of the genetic algorithm, such as population size, number of iterations, crossover probability, and mutation probability;

[0044] Initialize the population, which means generating a set of random grid-connected model parameters as the initial solution.

[0045] The fitness function is used to evaluate the fitness value of each individual in the current population. The individual's parameters are substituted into the grid-connected model to calculate the error between the model output and the actual data, and the fitness value is calculated based on the error.

[0046] Based on fitness values, select superior individuals as parents and perform crossover operations to generate new offspring;

[0047] The offspring individuals are subjected to mutation operations, that is, the values ​​of some of their genes are randomly changed, and the process of selection and crossover mutation is repeated until the predetermined number of iterations is reached;

[0048] After the iteration is completed, the individual with the lowest fitness value is selected from the population as the optimal solution, which is the optimized grid connection model parameter.

[0049] The optimized grid-connected model parameters are output and used in the subsequent grid-connected control of the photovoltaic synchronous machine power generation system.

[0050] The beneficial effects of this invention;

[0051] This invention significantly improves the grid connection stability of photovoltaic (PV) power generation systems by real-time monitoring and adjustment of the output voltage, frequency, and phase of the PV synchronous generator stack. The parameters of this invention are highly matched with grid parameters. By optimizing the grid connection control parameters using a random forest model and a genetic algorithm, this invention can reduce output voltage errors, frequency errors, and phase adjustment errors, making the power quality output by the PV power generation system more in line with grid standards.

[0052] This invention can collect photovoltaic array operation data and natural environment data in real time, and make predictions through a preset photovoltaic array power generation prediction model, so that the system can adapt to different lighting conditions and environmental changes, thereby enhancing the system's adaptability and robustness.

[0053] When the real-time photovoltaic array operating data exceeds the predicted data, the system generates an early warning message to remind maintenance personnel to handle the abnormal situation in a timely manner, preventing system overload or damage, thereby effectively protecting the photovoltaic power generation system. By precisely controlling the output parameters of the photovoltaic synchronous machine stack power generation system, this invention enables the photovoltaic power generation system to synchronize with the grid more efficiently, reducing energy loss during grid connection and improving the overall grid connection efficiency of the system.

[0054] This invention combines multiple technologies such as data acquisition, model prediction, real-time monitoring, and optimization algorithms to provide strong support for the intelligent operation and maintenance of photovoltaic power generation systems, reduce operation and maintenance costs, and improve operation and maintenance efficiency.

[0055] In summary, this invention effectively solves the problems existing in the grid connection process of photovoltaic synchronous machine power generation systems through a series of innovative technical means, improves the stability, adaptability and grid connection efficiency of photovoltaic power generation systems, and provides a strong guarantee for the sustainable development of the photovoltaic power generation industry. Attached Figure Description

[0056] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on the drawings without creative effort.

[0057] Figure 1 This is a schematic diagram of the grid connection control method for a photovoltaic synchronous generator stack power generation system provided in an embodiment of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention. The technical solutions provided by various embodiments of this invention will be described in detail below with reference to the accompanying drawings.

[0059] To better understand the purpose of this invention, the invention will now be described in further detail.

[0060] The grid-connected control method for a photovoltaic synchronous generator stack power generation system provided by the present invention includes:

[0061] Step S101: Obtain photovoltaic system data and photovoltaic power generation task data. The photovoltaic system data includes control commands, photovoltaic module data, inverter data, meteorological data, power generation data, and grid connection control data. Preprocess the photovoltaic system data and photovoltaic power generation task data to obtain preprocessed photovoltaic system data and photovoltaic power generation task data. Train the random forest model with the preprocessed photovoltaic system data and photovoltaic power generation task data to obtain the grid connection model of the photovoltaic synchronous machine stack power generation system.

[0062] In step S101, the present invention constructs a grid-connected model of a photovoltaic synchronous generator stack power generation system through the following specific steps to solve the problem of mismatch between the generator's output voltage, frequency, and phase and the power grid during the grid connection process of the photovoltaic power generation system:

[0063] Acquire photovoltaic system data, including control commands, photovoltaic module data (such as power, efficiency, and temperature), inverter data (such as inverter conversion efficiency and inverter operating status), meteorological data (such as solar irradiance, temperature, and wind speed), power generation data, and grid connection control data (such as grid connection voltage, grid connection current, and grid connection frequency).

[0064] Obtain photovoltaic power generation task data, including expected power generation, power generation period, and power regulation requirements.

[0065] The collected photovoltaic system data and photovoltaic power generation task data are preprocessed to remove noise, fill missing values, normalize or standardize the data, and improve the data quality.

[0066] The random forest model is trained using preprocessed photovoltaic system data and photovoltaic power generation task data as input. The random forest model is an ensemble learning method that improves the accuracy and stability of the model by constructing multiple decision trees and combining their predictions. After training, the random forest model becomes the grid-connected model for the photovoltaic synchronous machine stack power generation system, capable of receiving new photovoltaic system data and photovoltaic power generation task data, and outputting corresponding grid-connected control parameters.

[0067] Through step S101, this invention constructs a grid-connected model for a photovoltaic synchronous generator stack power generation system based on random forest. This model can comprehensively consider various photovoltaic system data and power generation task requirements, outputting grid-connected control parameters that meet grid requirements, thus providing an accurate basis for subsequent grid-connected control of the photovoltaic power generation system. This not only solves the problem of mismatch between the generator's output voltage, frequency, and phase and the grid, but also improves the stability of the photovoltaic power generation system.

[0068] Step S102: Collect photovoltaic array operation data and natural environment data, and substitute the collected photovoltaic array operation data and natural environment data into the preset photovoltaic array power generation prediction model to obtain photovoltaic array power generation prediction data.

[0069] The system collects operational data from the photovoltaic (PV) array, including real-time parameters such as voltage, current, power, and temperature of the PV modules. This data reflects the current operating status and power generation capacity of the PV array. Simultaneously, it collects environmental data, such as solar irradiance, temperature, and wind speed. This data directly impacts the power generation efficiency of the PV array, as the power generation capacity of PV modules is affected by environmental factors such as sunlight intensity and temperature.

[0070] The collected photovoltaic array operation data and natural environment data are input into a pre-set photovoltaic array power generation prediction model. This prediction model is based on historical data, system characteristics, and environmental factors, and can accurately predict the power generation of the photovoltaic array. After the prediction model is started, the input data is processed and analyzed to calculate the predicted power generation data of the photovoltaic array. This data includes the predicted power generation, power generation efficiency, and power output, providing important reference for subsequent grid connection control.

[0071] Through step S102, the present invention can obtain timely power generation prediction data of the photovoltaic array, providing an important reference for subsequent grid connection control. This helps the system understand the power generation capacity of the photovoltaic array in advance, thereby better adjusting grid connection control parameters and ensuring the stable and efficient synchronous operation of the photovoltaic power generation system with the grid. Simultaneously, it also provides strong support for responding to emergencies (such as sudden changes in the photovoltaic array's power generation capacity due to weather changes), enabling the system to respond quickly and ensuring the smooth progress of the grid connection process.

[0072] Step S103: Obtain real-time photovoltaic array operation data, substitute the real-time photovoltaic array operation data into the photovoltaic array power generation prediction data and compare it. If the real-time photovoltaic array operation data is higher than the photovoltaic array power generation prediction data, then generate photovoltaic array power generation early warning information.

[0073] The system collects real-time operating data of the photovoltaic array, including but not limited to parameters such as voltage, current, power output, and module temperature of the photovoltaic modules, reflecting the current actual working status and power generation capacity of the photovoltaic array.

[0074] The collected real-time photovoltaic array operation data is compared with the photovoltaic array power generation prediction data obtained through a pre-set photovoltaic array power generation prediction model. This comparison process aims to assess the difference between the actual power generation and the expected power generation.

[0075] If the real-time operating data of the photovoltaic array exceeds the predicted power generation data, the system determines that the current power generation capacity of the photovoltaic array exceeds the expected range. In this case, the system generates a power generation warning message for the photovoltaic array. The warning message typically includes key information such as the specific time the warning was triggered, the specific parameters that exceeded the expectations (such as power output, voltage, etc.), and the warning level, so that operation and maintenance personnel can understand and respond to abnormal situations in a timely manner.

[0076] Through step S103, the present invention realizes the real-time monitoring and early warning function of real-time photovoltaic array operation data. The generation of early warning information also provides decision support for operation and maintenance personnel, enabling them to take corresponding countermeasures according to the early warning level and specific circumstances, thereby ensuring the continuous operation of the photovoltaic power generation system.

[0077] Step S104: If the real-time photovoltaic array operation data is lower than the photovoltaic array power generation prediction data, then substitute the real-time photovoltaic array operation data into the grid connection model of the photovoltaic synchronous machine stack power generation system and output the grid connection control parameters of the photovoltaic synchronous machine stack power generation system.

[0078] When the real-time photovoltaic array operating data is lower than the predicted data, the system substitutes this data into the photovoltaic synchronous machine stack power generation system grid-connected model previously trained in step S101. The photovoltaic synchronous machine stack power generation system grid-connected model is built based on the random forest algorithm, which can comprehensively consider multiple factors (such as photovoltaic system data, power generation task data, etc.) to output grid-connected control parameters that meet the grid requirements.

[0079] After receiving real-time photovoltaic array operation data, the grid-connected model of the photovoltaic synchronous machine (PVM) power generation system performs a series of calculations and analyses, ultimately outputting the grid-connected control parameters of the PVM power generation system. These grid-connected control parameters include, but are not limited to, output voltage, frequency, and phase adjustment, which together determine the output characteristics of the PVM power generation system, enabling it to synchronize with the power grid.

[0080] Through step S104, this invention can promptly adjust the output characteristics of the photovoltaic synchronous machine stack power generation system when the real-time photovoltaic array operating data is lower than expected, enabling the photovoltaic synchronous machine stack power generation system to operate synchronously with the power grid. This not only improves the stability and grid connection efficiency of the photovoltaic power generation system but also helps reduce power quality problems caused by system mismatch. Furthermore, since the grid connection control parameters are dynamically generated based on real-time data, the system can better adapt to various operating conditions and environmental changes.

[0081] Step S105: Compare the grid-connected control parameters of the photovoltaic synchronous machine stack power generation system with the real-time parameters of the photovoltaic synchronous machine stack power generation system to obtain the parameter comparison error. The parameter comparison error includes output voltage error, frequency error, and phase adjustment error. Obtain historical data of photovoltaic array operation data. Use the historical data of photovoltaic array operation data and the parameter comparison error to optimize the grid-connected model of the photovoltaic synchronous machine stack power generation system using a genetic algorithm. Use the optimized grid-connected model of the photovoltaic synchronous machine stack power generation system to process the real-time photovoltaic array operation data and output the optimized real-time parameters of the photovoltaic synchronous machine stack power generation system. The photovoltaic synchronous machine stack power generation system executes the optimized real-time parameters to achieve synchronization with the grid, converting the electrical energy generated by the photovoltaic synchronous machine stack power generation system into AC power that conforms to the grid standard and realizing the connection with the grid.

[0082] The system compares the grid-connected control parameters of the photovoltaic synchronous generator stack (including output voltage, frequency, and phase adjustment) with the system's real-time parameters (i.e., the current output voltage, frequency, and phase). Through this comparison, the system calculates the parameter comparison errors, which include output voltage error, frequency error, and phase adjustment error. These errors reflect the differences between the current system output and the desired grid-connected control parameters.

[0083] The system acquires historical data on the photovoltaic array's operation, including its performance over a past period. By combining this data with previously calculated parameter comparison errors, the system plans to use this information to optimize the grid-connected model of the photovoltaic synchronous generator stack power generation system.

[0084] The system utilizes a genetic algorithm to optimize the grid-connected model of a photovoltaic synchronous generator stack. A genetic algorithm is a search algorithm that simulates natural selection and genetic mechanisms. Through continuous iteration and optimization, it can find the parameter combination that minimizes the error between the model output and the actual data. During the optimization process, the system constructs a fitness function based on the optimization objective (such as minimizing the weighted sum of output voltage error, frequency error, and phase adjustment error) to evaluate the model's performance under different parameter combinations.

[0085] Through operations such as selection, crossover, and mutation, genetic algorithms gradually optimize model parameters until a predetermined number of iterations is reached or the convergence condition is met.

[0086] After optimization, the system uses the optimized photovoltaic synchronous machine stack power generation system grid connection model to process the real-time photovoltaic array operation data.

[0087] The model outputs optimized real-time parameters of the photovoltaic synchronous machine stack power generation system, which more accurately reflect the grid requirements and the actual state of the system.

[0088] The photovoltaic synchronous generator system executes these optimized real-time parameters to achieve synchronization with the power grid. By adjusting parameters such as output voltage, frequency, and phase, the system can convert the generated electrical energy into AC power that conforms to grid standards and achieve a stable connection with the grid.

[0089] Through step S105, this invention not only achieves real-time monitoring and optimization of grid-connected parameters for photovoltaic synchronous generator systems, but also improves the accuracy of the model through advanced technologies such as genetic algorithms. This helps ensure the stable operation of photovoltaic power generation systems under different operating conditions and environmental conditions, improving grid connection efficiency and power quality.

[0090] Specifically, in the grid-connected control method for a photovoltaic synchronous generator stack power generation system according to the present invention, step S101 includes:

[0091] The data for the photovoltaic modules includes power, efficiency, and temperature;

[0092] Inverter data includes inverter conversion efficiency and inverter operating status;

[0093] Meteorological data includes solar irradiance, temperature, and wind speed;

[0094] Grid connection control data includes grid connection voltage, grid connection current, and grid connection frequency;

[0095] Photovoltaic power generation task data includes expected power generation, power generation period, and power regulation requirements;

[0096] The random forest model is trained using preprocessed photovoltaic system data and photovoltaic power generation task data as input. After training, the random forest model becomes the grid-connected model of the photovoltaic synchronous machine stack power generation system, which is used to receive new photovoltaic system data and photovoltaic power generation task data, and output grid-connected control parameters.

[0097] In the detailed description of step S101, the grid-connected control method for a photovoltaic synchronous machine power generation system of the present invention further clarifies the specific content of photovoltaic system data and photovoltaic power generation task data, as well as how to use the data to train a random forest model, thereby constructing a grid-connected model for the photovoltaic synchronous machine power generation system. The following is a detailed explanation of this step:

[0098] Photovoltaic module data:

[0099] Power: The current output power of the photovoltaic module.

[0100] Efficiency: The efficiency with which a photovoltaic module converts light energy into electrical energy.

[0101] Temperature: The operating temperature of photovoltaic modules affects efficiency and power output.

[0102] Inverter data:

[0103] Inverter conversion efficiency: The efficiency with which an inverter converts direct current (DC) to alternating current (AC).

[0104] Inverter operating status: This includes status information such as whether the inverter is operating normally and whether there are any fault alarms.

[0105] Meteorological data:

[0106] Solar irradiance: The intensity of sunlight hitting a photovoltaic module.

[0107] Temperature: Ambient temperature affects the performance of photovoltaic modules and inverters.

[0108] Wind speed: can affect the cooling effect of photovoltaic modules and the overall heat dissipation of the system.

[0109] Grid connection control data:

[0110] Grid-connected voltage: The voltage output by the photovoltaic power generation system to the power grid.

[0111] Grid-connected current: The current output from the photovoltaic power generation system to the power grid.

[0112] Grid connection frequency: The frequency of AC power output from the photovoltaic power generation system to the power grid.

[0113] Photovoltaic power generation task data:

[0114] Expected power generation: The total amount of electricity to be generated within a certain period of time.

[0115] Power generation period: The specified time range for power generation.

[0116] Power regulation requirements: The requirements for adjusting the output power according to the grid demand or system conditions.

[0117] The collected photovoltaic system data and photovoltaic power generation task data are cleaned, denoised, and normalized or standardized to improve the model training effect. The preprocessed data is then used as input to train the random forest model. Random forest is an ensemble learning method that improves the accuracy and stability of the model by constructing multiple decision trees and combining their prediction results. After training, the random forest model becomes the grid-connected model for the photovoltaic synchronous machine stack power generation system. This model can receive new photovoltaic system data and photovoltaic power generation task data, and output grid-connected control parameters, such as adjusted grid-connected voltage, grid-connected current, and grid-connected frequency, to ensure that the photovoltaic power generation system can achieve stable and efficient synchronization with the power grid.

[0118] Through the detailed implementation of step S101, this invention constructs a grid-connected model of a photovoltaic synchronous generator stack power generation system based on random forest, providing an accurate basis for subsequent grid-connected control of the photovoltaic power generation system.

[0119] Specifically, in the grid-connected control method for a photovoltaic synchronous generator stack power generation system according to the present invention, step S102 includes:

[0120] The operating data of the photovoltaic array includes real-time parameters such as the voltage, current, power, and temperature of the photovoltaic modules.

[0121] The preprocessed photovoltaic array operation data and natural environment data are used as inputs and substituted into the preset photovoltaic array power generation prediction model. The preset photovoltaic array power generation prediction model is started to process the input data and calculate the photovoltaic array power generation prediction data through the preset photovoltaic array power generation prediction model. The photovoltaic array power generation prediction data includes the predicted power generation, the predicted power efficiency, and the predicted power output.

[0122] In the detailed description of step S102, the grid-connected control method for a photovoltaic synchronous machine power generation system of the present invention further clarifies the specific content of the photovoltaic array operation data, and how to use these data and environmental data to start and run a preset photovoltaic array power generation prediction model, thereby obtaining the photovoltaic array power generation prediction data. The following is a detailed explanation of this step:

[0123] Operating data of the photovoltaic array:

[0124] Photovoltaic module voltage: The current output voltage value of the photovoltaic module.

[0125] Photovoltaic module current: The current value currently output by the photovoltaic module.

[0126] Photovoltaic module power: The current output power of a photovoltaic module, usually the product of voltage and current.

[0127] Real-time photovoltaic module temperature parameters: The operating temperature of the photovoltaic module directly affects its efficiency and power output. Simultaneously, we continue to collect natural environmental data, including solar irradiance, temperature, and wind speed.

[0128] The collected photovoltaic array operation data and natural environment data undergo necessary preprocessing, such as cleaning, noise reduction, normalization, or standardization, to ensure data accuracy. The preprocessed photovoltaic array operation data and natural environment data are then used as input to a pre-defined photovoltaic array power generation prediction model. The pre-defined photovoltaic array power generation prediction model is then activated to process and analyze the input data. This model may be built based on machine learning, deep learning, or other statistical methods, and can comprehensively consider multiple factors to predict the power generation of the photovoltaic array. The pre-defined photovoltaic array power generation prediction model calculates the predicted power generation data for the photovoltaic array. This data includes:

[0129] Projected power generation: The expected power generation of the photovoltaic array over a future period of time (such as a day, a week, or a month).

[0130] Predicted power generation efficiency: The predicted efficiency of a photovoltaic array in converting light energy into electrical energy.

[0131] Predicted power output: The predicted power output value of the photovoltaic array at a certain point in time or within a certain period of time in the future.

[0132] Through the detailed implementation of step S102, the present invention can accurately predict the power generation of the photovoltaic array, providing an important reference for subsequent grid connection control. This helps the system to understand the power generation capacity of the photovoltaic array in advance, thereby better adjusting the grid connection control parameters and improving the stable and efficient synchronous operation of the photovoltaic power generation system with the grid.

[0133] Specifically, in the grid-connected control method for a photovoltaic synchronous generator stack power generation system according to the present invention, step S103 includes:

[0134] The prediction data for the corresponding time period is obtained from the photovoltaic array power generation prediction model. The real-time photovoltaic array operation data and the photovoltaic array power generation prediction data are aligned in time, that is, the real-time photovoltaic array operation data and the photovoltaic array power generation prediction data correspond to the data at the same point in time or within the same time period.

[0135] The real-time photovoltaic array operation data is compared with the photovoltaic array power generation prediction data item by item to check whether the parameters of the real-time photovoltaic array are higher than the predicted values.

[0136] An early warning is triggered when the power output of the real-time photovoltaic array exceeds the predicted power by 10% for 5 consecutive minutes. The warning includes the triggering time, parameters, and warning level information.

[0137] Predicted data for the corresponding time period is obtained from the photovoltaic array power generation prediction model, so that the real-time photovoltaic array operation data and the predicted data are aligned in time, and that the two correspond to the data of the same point in time or time period, so as to make accurate comparison and analysis.

[0138] The real-time photovoltaic array operating data is compared item by item with the photovoltaic array power generation prediction data, including parameters such as voltage, current, power, and temperature. It is then checked whether each parameter of the real-time photovoltaic array exceeds the predicted value. This comparison helps identify the differences between the actual operating data and the predicted data, as well as potential problems or areas for optimization.

[0139] The early warning mechanism is triggered when the real-time power output of the photovoltaic array exceeds 10% of the predicted power for five consecutive minutes. This threshold (10%) and time window (5 minutes) are set based on system characteristics and operational experience to ensure the accuracy and timeliness of the early warning.

[0140] The early warning information includes the time when the warning was triggered, the parameters (such as power, voltage, etc.), and the warning level. Warning levels can be categorized based on the actual situation, such as low-level, medium-level, and high-level warnings, to reflect the severity and urgency of the problem.

[0141] When an alert is triggered, the system should immediately take appropriate measures, including adjusting the operating parameters of the photovoltaic array, checking the system status, and investigating potential faults. Simultaneously, the system should record the alert information for subsequent analysis and improvement.

[0142] By implementing step S103, the present invention can promptly identify the difference between the actual operation and prediction of the photovoltaic array, and remind operators or the system to take corresponding measures automatically through the early warning mechanism, thereby ensuring the stable operation and efficient grid connection of the photovoltaic power generation system.

[0143] Specifically, in the grid-connected control method for a photovoltaic synchronous generator stack power generation system according to the present invention, step S104 includes:

[0144] To determine whether the real-time photovoltaic array operating data is lower than the photovoltaic array power generation prediction data, the voltage, current, and power of the real-time photovoltaic array operating data are compared with the photovoltaic array power generation prediction data. If the real-time photovoltaic array operating data is lower than the prediction data, the voltage, current, and power of the real-time photovoltaic array operating data are used as input information.

[0145] The grid connection model of the photovoltaic synchronous machine stack power generation system to be used is determined. The grid connection model of the photovoltaic synchronous machine stack power generation system is established based on historical data, system characteristics and control objectives. The grid connection model of the photovoltaic synchronous machine stack power generation system is used to output grid connection control parameters.

[0146] The real-time photovoltaic array operation data is substituted into the grid-connected model of the photovoltaic synchronous machine stack power generation system, and the voltage, current, and timestamp of the data are correlated with the input variables of the model.

[0147] The grid-connected model of the photovoltaic synchronous machine stack power generation system is started. The grid-connected model of the photovoltaic synchronous machine stack power generation system processes the input real-time photovoltaic array operation data and calculates the grid-connected control parameters.

[0148] The grid-connection control parameters are obtained from the grid-connection model of the photovoltaic synchronous machine stack power generation system. The grid-connection control parameters include output voltage, frequency and phase adjustment. The grid-connection control parameters are used to adjust the output of the photovoltaic synchronous machine stack power generation system so that the photovoltaic synchronous machine stack power generation system is synchronized with the grid.

[0149] Determine if the real-time photovoltaic array operating data (including voltage, current, and power) is lower than the predicted photovoltaic array power generation data. If the real-time photovoltaic array operating data is lower than the predicted data, it indicates that the current system's power generation capacity has not met expectations and adjustments are needed. Use the voltage, current, and power data of the real-time photovoltaic array operating data as input information for subsequent calculations.

[0150] Determine the grid-connected model for the photovoltaic synchronous machine (PVMT) power generation system to be used. This model is built based on historical data, system characteristics, and control objectives, and can output grid-connected control parameters for adjusting the system output. Substitute real-time PV array operating data into the PVMT power generation system grid-connected model. Ensure that the voltage, current, and timestamps of the data correspond to the model's input variables so that the model can accurately process the data. Start the PVMT power generation system grid-connected model to process the input real-time PV array operating data.

[0151] The grid-connected model of the photovoltaic synchronous machine (PVM) power generation system processes the input real-time operating data of the photovoltaic array and calculates the grid-connected control parameters based on the model's algorithms and logic. The output grid-connected control parameters, including output voltage, frequency, and phase adjustment, are obtained from the PVM power generation system grid-connected model. These parameters are crucial information used to adjust the output of the PVM power generation system to ensure its synchronization with the grid.

[0152] The calculated grid-connected control parameters are applied to the photovoltaic synchronous generator system, adjusting the system's output voltage, frequency, and phase to ensure consistency with the corresponding parameters of the power grid. Based on the system's actual operating conditions and the grid's demands, the grid-connected control parameters are continuously adjusted to ensure the photovoltaic power generation system can operate stably and efficiently in sync with the grid.

[0153] By implementing step S104, this invention can calculate accurate grid connection control parameters based on real-time photovoltaic array operation data and the grid connection model of the photovoltaic synchronous generator stack power generation system, thereby achieving synchronous operation of the photovoltaic power generation system and the power grid. This helps improve the grid connection efficiency of the photovoltaic power generation system and reduce the risks and costs during the grid connection process.

[0154] Specifically, in the grid-connected control method for a photovoltaic synchronous generator stack power generation system according to the present invention, step S105 includes:

[0155] Obtain the grid-connected control parameters of the photovoltaic synchronous machine stack power generation system output by step S104. The grid-connected control parameters of the photovoltaic synchronous machine stack power generation system are calculated based on the grid-connected model of the photovoltaic synchronous machine stack power generation system, and are intended to synchronize the system output with the grid.

[0156] The actual operating parameters of the photovoltaic synchronous machine stack power generation system are acquired in real time. The actual operating parameters of the photovoltaic synchronous machine stack power generation system include the current output voltage, frequency and phase.

[0157] The grid-connected control parameters and the real-time system parameters are aligned in time, meaning that the grid control parameters and the real-time parameters of the photovoltaic synchronous machine stack power generation system correspond to the same moment.

[0158] The target output voltage, target frequency, and target phase in the grid-connected control parameters are compared item by item with the actual output voltage, actual frequency, and actual phase in the real-time parameters of the photovoltaic synchronous machine stack power generation system. The error value of each parameter is calculated, which is the difference between the real-time value of the photovoltaic synchronous machine stack power generation system and the target value in the grid-connected control parameters.

[0159] For the output voltage, calculate the difference between the actual output voltage and the target output voltage to obtain the output voltage error;

[0160] For frequency, the difference between the actual frequency and the target frequency is calculated to obtain the frequency error;

[0161] For the phase, the difference between the actual phase and the target phase is calculated to obtain the phase adjustment error.

[0162] Real-time acquisition of actual operating parameters of the photovoltaic synchronous machine stack power generation system, including the current output voltage, frequency, and phase, reflects the current operating status of the system. This ensures that the grid-connected control parameters and the actual operating parameters of the system are aligned in time, meaning that they correspond to data at the same moment. This helps to accurately assess the difference between the current state and the expected state of the system.

[0163] Output voltage comparison and error calculation: The target output voltage in the grid-connected control parameters is compared with the actual output voltage in the actual operating parameters of the system, and the difference between the two is calculated to obtain the output voltage error.

[0164] Frequency comparison and error calculation: The target frequency in the grid-connected control parameters is compared with the actual frequency in the actual operating parameters of the system, and the difference between the two is calculated to obtain the frequency error.

[0165] Phase comparison and error calculation compare the target phase in the grid-connected control parameters with the actual phase in the actual operating parameters of the system, calculate the difference between the two, and obtain the phase adjustment error.

[0166] The calculated error values ​​(output voltage error, frequency error, phase adjustment error) reflect the difference between the current state and the expected state of the system. The error values ​​can be used for subsequent control strategy adjustments to reduce the difference and achieve synchronization between the system output and the power grid.

[0167] By implementing step S105, the present invention can accurately assess the difference between the current state and the expected state of the photovoltaic synchronous generator system, and provide an important basis for subsequent control strategy adjustments, which helps the system output to synchronize with the grid and improves the stability and grid connection efficiency of the photovoltaic power generation system.

[0168] Specifically, in the grid-connected control method for a photovoltaic synchronous generator stack power generation system according to the present invention, step S105 includes:

[0169] Based on the grid connection requirements and control objectives of the photovoltaic synchronous machine stack power generation system, the optimization objectives are determined. The optimization objectives include minimizing the weighted sum of output voltage error, frequency error and phase adjustment error, as well as the error threshold.

[0170] Based on the optimization objective, a fitness function is constructed, which is used to evaluate the grid-connected model under given parameters;

[0171] Determine the parameters of the genetic algorithm, such as population size, number of iterations, crossover probability, and mutation probability;

[0172] Initialize the population, which means generating a set of random grid-connected model parameters as the initial solution.

[0173] The fitness function is used to evaluate the fitness value of each individual in the current population. The individual's parameters are substituted into the grid-connected model to calculate the error between the model output and the actual data, and the fitness value is calculated based on the error.

[0174] Based on fitness values, select superior individuals as parents and perform crossover operations to generate new offspring;

[0175] The offspring individuals are subjected to mutation operations, that is, the values ​​of some of their genes are randomly changed, and the process of selection and crossover mutation is repeated until the predetermined number of iterations is reached;

[0176] After the iteration is completed, the individual with the lowest fitness value is selected from the population as the optimal solution, which is the optimized grid connection model parameter.

[0177] The optimized grid-connected model parameters are output and used in the subsequent grid-connected control of the photovoltaic synchronous machine power generation system.

[0178] Based on the grid connection requirements and control objectives of the photovoltaic synchronous generator system, the optimization objective is clearly defined as minimizing the weighted sum of output voltage error, frequency error, and phase adjustment error. Simultaneously, an error threshold is set as a constraint in the optimization process.

[0179] Based on the optimization objective, a fitness function is constructed. This function should be able to evaluate the performance of the grid-connected model under given parameters, that is, calculate the error between the model output and the actual data, and calculate the fitness value based on the error. The lower the fitness value, the better the model performance.

[0180] The parameters of the genetic algorithm are determined, including the population size (i.e., the number of initial solutions), the number of iterations (i.e., the total number of rounds in the optimization process), the crossover probability (i.e., the probability that two parent individuals cross to generate offspring), and the mutation probability (i.e., the probability that an individual's genes will undergo random changes).

[0181] A set of random grid-connected model parameters is generated as the initial solution to form the initial population. These parameters may include various coefficients, thresholds, etc. in the grid-connected model.

[0182] The fitness function is used to evaluate the fitness value of each individual in the current population. The individual's parameters are substituted into the grid-connected model, the error between the model output and the actual data is calculated, and the fitness value is calculated based on the error.

[0183] Individuals with high fitness values ​​are selected as parents. Generally, individuals with lower fitness values ​​are more likely to be selected.

[0184] Crossover is performed on selected parent individuals to generate new offspring. Crossover can be achieved by exchanging some genes between parent individuals.

[0185] Mutation operations are performed on offspring individuals, which randomly change the values ​​of some of their genes. Mutation operations help increase population diversity and prevent the optimization process from getting trapped in local optima.

[0186] The process of selection and crossover mutation is repeated until a predetermined number of iterations is reached. In each iteration, a new population is generated, and its fitness value is evaluated. Through continuous iteration, the individuals in the population gradually approach the optimal solution.

[0187] After the iteration is complete, the individual with the lowest fitness value is selected from the population as the optimal solution. This optimal solution is the optimized grid connection model parameter.

[0188] The optimized grid-connected model parameters are output and used in the subsequent grid-connected control of the photovoltaic synchronous machine power generation system. The optimized parameters can further improve the accuracy and stability of grid-connected control.

[0189] By implementing step S105, the present invention can optimize the grid-connected model parameters using a genetic algorithm, thereby reducing output voltage error, frequency error and phase adjustment error, and improving the accuracy and stability of grid connection of the photovoltaic synchronous generator stack power generation system.

[0190] The grid-connected control method for photovoltaic synchronous generator stack power generation system of the present invention effectively solves the problems of unstable generator output voltage and mismatch between generator output voltage, frequency and phase and grid voltage, frequency and phase during the grid connection process of existing photovoltaic synchronous generator stack power generation systems through the following technical means:

[0191] Acquire photovoltaic system data (including control commands, photovoltaic module data, inverter data, meteorological data, power generation data, and grid connection control data) and photovoltaic power generation task data, and perform preprocessing.

[0192] A random forest model was trained using the preprocessed data to obtain the grid-connected model of the photovoltaic synchronous machine stack power generation system. This model can accurately receive and process new photovoltaic system data and photovoltaic power generation task data, and output accurate grid-connected control parameters.

[0193] By collecting operational data and natural environmental data from the photovoltaic array, and inputting them into a pre-set photovoltaic array power generation prediction model, the predicted power generation data of the photovoltaic array can be obtained. This prediction model allows for an early understanding of the photovoltaic array's power generation capacity, providing crucial information for subsequent grid-connected control.

[0194] The system acquires real-time photovoltaic (PV) array operating data and compares it with PV array power generation prediction data. If the real-time PV array operating data exceeds the prediction data, an early warning message is generated, which helps to promptly detect and handle abnormal situations and prevent system overload or damage.

[0195] If the real-time photovoltaic array operating data is lower than the predicted data, the real-time photovoltaic array operating data is substituted into the grid-connected model of the photovoltaic synchronous machine power generation system to output grid-connected control parameters. The grid-connected control parameters are compared with the real-time system parameters to calculate the parameter comparison error (including output voltage error, frequency error, and phase adjustment error). A genetic algorithm is used to optimize the grid-connected model, continuously adjusting the model parameters based on historical data and parameter comparison errors to improve the accuracy and stability of grid-connected control.

[0196] The optimized grid-connected model processes real-time photovoltaic array operating data and outputs optimized real-time parameters. The photovoltaic synchronous machine stack power generation system executes the optimized real-time parameters to achieve synchronization with the grid, converting the generated electrical energy into AC power that conforms to grid standards, and achieving grid connection.

[0197] Through these steps, the method of the present invention can monitor and adjust the output of the photovoltaic synchronous generator stack in real time, ensuring that the generator's output voltage, frequency and phase are highly matched with the grid, thereby solving the problems of unstable output voltage and parameter mismatch in the prior art, and improving the stability and grid connection efficiency of the photovoltaic power generation system.

Claims

1. A grid-connected control method for a photovoltaic synchronous generator stack power generation system, characterized in that, include: Step S101: Obtain photovoltaic system data and photovoltaic power generation task data. The photovoltaic system data includes control commands, photovoltaic module data, inverter data, meteorological data, power generation data, and grid connection control data. Preprocess the photovoltaic system data and photovoltaic power generation task data to obtain preprocessed photovoltaic system data and photovoltaic power generation task data. Train the random forest model with the preprocessed photovoltaic system data and photovoltaic power generation task data to obtain the grid connection model of the photovoltaic synchronous machine stack power generation system. Step S102: Collect photovoltaic array operation data and natural environment data, and substitute the collected photovoltaic array operation data and natural environment data into the preset photovoltaic array power generation prediction model to obtain photovoltaic array power generation prediction data. Step S103: Obtain real-time photovoltaic array operation data, substitute the real-time photovoltaic array operation data into the photovoltaic array power generation prediction data and compare it. If the real-time photovoltaic array operation data is higher than the photovoltaic array power generation prediction data, then generate photovoltaic array power generation early warning information. Step S104: If the real-time photovoltaic array operation data is lower than the photovoltaic array power generation prediction data, then substitute the real-time photovoltaic array operation data into the grid connection model of the photovoltaic synchronous machine stack power generation system and output the grid connection control parameters of the photovoltaic synchronous machine stack power generation system. Step S105: Compare the grid-connected control parameters of the photovoltaic synchronous machine stack power generation system with the real-time parameters of the photovoltaic synchronous machine stack power generation system to obtain the parameter comparison error. The parameter comparison error includes output voltage error, frequency error and phase adjustment error. Obtain historical data of photovoltaic array operation data. Use the historical data of photovoltaic array operation data and the parameter comparison error to optimize the grid-connected model of the photovoltaic synchronous machine stack power generation system using a genetic algorithm. Use the optimized grid-connected model of the photovoltaic synchronous machine stack power generation system to process the real-time photovoltaic array operation data and output the optimized real-time parameters of the photovoltaic synchronous machine stack power generation system. The photovoltaic synchronous machine stack power generation system executes the optimized real-time parameters of the photovoltaic synchronous machine stack power generation system to achieve synchronization with the grid. Convert the electrical energy generated by the photovoltaic synchronous machine stack power generation system into AC power that conforms to the grid standard and realize the connection with the grid. Step S105 includes: Obtain the grid-connected control parameters of the photovoltaic synchronous machine stack power generation system output by step S104. The grid-connected control parameters of the photovoltaic synchronous machine stack power generation system are calculated based on the grid-connected model of the photovoltaic synchronous machine stack power generation system, and are intended to synchronize the system output with the grid. The actual operating parameters of the photovoltaic synchronous machine stack power generation system are acquired in real time. The actual operating parameters of the photovoltaic synchronous machine stack power generation system include the current output voltage, frequency and phase. The grid-connected control parameters and the real-time system parameters are aligned in time, meaning that the grid-connected control parameters and the real-time parameters of the photovoltaic synchronous machine power generation system correspond to the same moment. The target output voltage, target frequency, and target phase in the grid-connected control parameters are compared item by item with the actual output voltage, actual frequency, and actual phase in the real-time parameters of the photovoltaic synchronous machine stack power generation system. The error value of each parameter is calculated, which is the difference between the real-time value of the photovoltaic synchronous machine stack power generation system and the target value in the grid-connected control parameters. For the output voltage, calculate the difference between the actual output voltage and the target output voltage to obtain the output voltage error; For frequency, the difference between the actual frequency and the target frequency is calculated to obtain the frequency error; For the phase, the difference between the actual phase and the target phase is calculated to obtain the phase adjustment error; Step S105 includes: Based on the grid connection requirements and control objectives of the photovoltaic synchronous machine stack power generation system, the optimization objectives are determined. The optimization objectives include minimizing the weighted sum of output voltage error, frequency error and phase adjustment error, as well as the error threshold. Based on the optimization objective, a fitness function is constructed, which is used to evaluate the grid-connected model under given parameters; Determine the parameters of the genetic algorithm, including population size, number of iterations, crossover probability, and mutation probability; Initialize the population, that is, generate a set of random grid-connected model parameters as the initial solution; The fitness function is used to evaluate the fitness value of each individual in the current population. The individual's parameters are substituted into the grid-connected model to calculate the error between the model output and the actual data, and the fitness value is calculated based on the error. Based on fitness values, select superior individuals as parents and perform crossover operations to generate new offspring; The offspring individuals are subjected to mutation operations, that is, the values ​​of some of their genes are randomly changed, and the process of selection and crossover mutation is repeated until the predetermined number of iterations is reached; After the iteration is completed, the individual with the lowest fitness value is selected from the population as the optimal solution, which is the optimized grid connection model parameter. The optimized grid-connected model parameters are output and used in the subsequent grid-connected control of the photovoltaic synchronous machine power generation system.

2. The grid-connected control method for a photovoltaic synchronous generator stack power generation system as described in claim 1, characterized in that, Step S101 includes: The data for the photovoltaic modules includes power, efficiency, and temperature; Inverter data includes inverter conversion efficiency and inverter operating status; Meteorological data includes solar irradiance, temperature, and wind speed; Grid connection control data includes grid connection voltage, grid connection current, and grid connection frequency; Photovoltaic power generation task data includes expected power generation, power generation period, and power regulation requirements; The random forest model is trained using preprocessed photovoltaic system data and photovoltaic power generation task data as input. After training, the random forest model becomes the grid-connected model of the photovoltaic synchronous machine stack power generation system, which is used to receive new photovoltaic system data and photovoltaic power generation task data, and output grid-connected control parameters.

3. The grid-connected control method for a photovoltaic synchronous generator stack power generation system as described in claim 1, characterized in that, Step S102 includes: The operating data of the photovoltaic array includes real-time parameters such as the voltage, current, power, and temperature of the photovoltaic modules. The pre-processed photovoltaic array operation data and natural environment data are used as inputs and substituted into the preset photovoltaic array power generation prediction model. The preset photovoltaic array power generation prediction model is started to process the input data and calculate the photovoltaic array power generation prediction data, which includes the predicted power generation, predicted power generation efficiency, and predicted power output.

4. The grid-connected control method for a photovoltaic synchronous generator stack power generation system as described in claim 1, characterized in that, Step S103 includes: The prediction data for the corresponding time period is obtained from the photovoltaic array power generation prediction model. The real-time photovoltaic array operation data and the photovoltaic array power generation prediction data are aligned in time, that is, the real-time photovoltaic array operation data and the photovoltaic array power generation prediction data correspond to the data at the same point in time or within the same time period. The real-time photovoltaic array operation data is compared with the photovoltaic array power generation prediction data item by item to check whether the parameters of the real-time photovoltaic array are higher than the predicted values. An early warning is triggered when the power output of the real-time photovoltaic array exceeds 10% of the predicted power for 5 consecutive minutes. The warning includes the triggering time, parameters, and warning level information.

5. The grid-connected control method for a photovoltaic synchronous generator stack power generation system as described in claim 1, characterized in that, Step S104 includes: To determine whether the real-time photovoltaic array operating data is lower than the photovoltaic array power generation prediction data, the voltage, current, and power of the real-time photovoltaic array operating data are compared with the photovoltaic array power generation prediction data. If the real-time photovoltaic array operating data is lower than the prediction data, the voltage, current, and power of the real-time photovoltaic array operating data are used as input information. The grid connection model of the photovoltaic synchronous machine stack power generation system to be used is determined. The grid connection model of the photovoltaic synchronous machine stack power generation system is established based on historical data, system characteristics and control objectives. The grid connection model of the photovoltaic synchronous machine stack power generation system is used to output grid connection control parameters. The real-time photovoltaic array operation data is substituted into the grid-connected model of the photovoltaic synchronous machine stack power generation system, and the voltage, current, and timestamp of the data are correlated with the input variables of the model. The grid-connected model of the photovoltaic synchronous machine stack power generation system is started. The grid-connected model of the photovoltaic synchronous machine stack power generation system processes the input real-time photovoltaic array operation data and calculates the grid-connected control parameters. The grid-connection control parameters are obtained from the grid-connection model of the photovoltaic synchronous machine stack power generation system. The grid-connection control parameters include output voltage, frequency and phase adjustment. The grid-connection control parameters are used to adjust the output of the photovoltaic synchronous machine stack power generation system so that the photovoltaic synchronous machine stack power generation system is synchronized with the grid.

Images